Deep Learning for Wind Speed Forecasting Using Bi-LSTM with Selected Features

Abstract

Wind speed forecasting is important for wind energy forecasting. In the modern era, the increase in energy demand can be managed effectively by forecasting the wind speed accurately. The main objective of this research is to improve the performance of wind speed forecasting by handling uncertainty, the curse of dimensionality, overfitting and non-linearity issues. The curse of dimensionality and overfitting issues are handled by using Boruta feature selection. The uncertainty and the non-linearity issues are addressed by using the deep learning based Bi-directional Long Short Term Memory (Bi-LSTM). In this paper, Bi-LSTM with Boruta feature selection named BFS-Bi-LSTM is proposed to improve the performance of wind speed forecasting. The model identifies relevant features for wind speed forecasting from the meteorological features using Boruta wrapper feature selection (BFS). Followed by Bi-LSTM predicts the wind speed by considering the wind speed from the past and future time steps. The proposed BFS-Bi-LSTM model is compared against Multilayer perceptron (MLP), MLP with Boruta (BFS-MLP), Long Short Term Memory (LSTM), LSTM with Boruta (BFS-LSTM) and Bi-LSTM in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Square Error (MSE) and R 2 . The BFS-Bi-LSTM surpassed other models by producing RMSE of 0.784, MAE of 0.530, MSE of 0.615 and R 2 of 0.8766. The experimental result shows that the BFS-Bi-LSTM produced better forecasting results compared to others.

Prediction of Particulate Matter PM2.5 Using Bidirectional Gated Recurrent Unit with Feature Selection

“…The model-based feature selection finds the subset of features that provides the highest model accuracy using the model as the internal feature selector. The subset with minimal error or highest accuracy is considered as the selected features (Subbiah et al, 2023)]. Thus, the random forest has both characteristics of feature selection.…”

Modeling Geometrically Nonlinear FG Plates: A Fast and Accurate Alternative to IGA Method Based on Deep Learning

“…Yildirim [42] suggested the use of novel, network-based, deep BLSTM wavelet sequences for classifying electrocardiogram signals, achieving 99.39% recognition and largely improving performance compared to conventional networks. Subbiah et al [43] developed a BLSTM scheme with Boruta feature selection to improve wind speed forecasting by exploiting past and future information. BLSTM schemes have been widely applied in fields like natural language processing [44], cardiac signal classification [42], and tourism forecast [45], whereas its use is not yet spread in the analysis of structural problems, as those we are dealing with in the present paper.…”

Multi-Step-Ahead Wind Speed Forecast System: Hybrid Multivariate Decomposition and Feature Selection-Based Gated Additive Tree Ensemble Model

“…The superior predictive performance of LSTM is due to its additional gates and memory cells, which offer added benefits in remembering longer sequences in data. LSTM can be further enhanced through bidirectional processing, enabling the network to capture information from past and future time steps [31]. This is evident in [18], where bidirectional LSTM (BiLSTM) outperformed LSTM, RNN, ANN, and RFR for short-term WS forecasting.…”

“…To achieve optimal model performance, relevant predictors must be selected using a suitable feature selection (FS) method. The efficacy of a wrapper-based Boruta FS technique is highlighted in [31], successfully addressing challenges related to the curse of dimensionality and overfitting. Another study [18] integrated Boruta with a filter-based RReliefF method for FS, achieving notably accurate results in short-term WS forecasting.…”